Urban areas extraction from multi sensor data based on machine learning and data fusion

Accurate urban areas information is important for a variety of applications, especially city planning and natural disaster prediction and management. In recent years, extraction of urban structures from remotely sensed images has been extensively explored. The key advantages of this imaging modality are reduction of surveying expense and time. It also elevates restrictions on ground surveys. Thus far, much research typically extracts these structures from very high resolution satellite imagery, which are unfortunately of relatively poor spectral resolution, resulting in good precision yet moderate accuracy. Therefore, this paper investigates extraction of buildings from middle and high resolution satellite images by using spectral indices (Normalized Difference Building Index: NDBI, Normalized Difference Vegetation Index: NDVI, Soil Adjustment Vegetation Index: SAVI, Modified Normalized Difference Index: MNDWI, and Global Environment Monitoring Index: GEMI) by means of various Machine Learning methods (Artificial Neural Network: ANN, K-Nearest Neighbor: KNN, and Support Vector Machine: SVM) and Data Fusion (i.e., Majority Voting). Herein empirical results suggested that suitable learning methods for urban areas extraction are in preferring order Data Fusion, SVM, KNN, and ANN. Their accuracies were 85.46, 84.86, 84.66, and 84.91%, respectively.

[1]  Zhengjun Liu,et al.  Building extraction from high resolution satellite imagery based on multi-scale image segmentation and model matching , 2008, 2008 International Workshop on Earth Observation and Remote Sensing Applications.

[2]  Mustafa Turker,et al.  Building extraction from high-resolution optical spaceborne images using the integration of support vector machine (SVM) classification, Hough transformation and perceptual grouping , 2015, Int. J. Appl. Earth Obs. Geoinformation.

[3]  R. Maurya,et al.  Building extraction from very high resolution multispectral images using NDVI based segmentation and morphological operators , 2012, 2012 Students Conference on Engineering and Systems.

[4]  J. A. Schell,et al.  Monitoring vegetation systems in the great plains with ERTS , 1973 .

[5]  Yang Shan,et al.  An Effective Approach to Automatically Extract Urban Land-use from TM lmagery , 2003, National Remote Sensing Bulletin.

[6]  Lobina G. Palamuleni,et al.  Developing remote sensing methodology to distinguish urban built-up areas and bare land in Mafikeng town, South Africa , 2014, 2014 IEEE Geoscience and Remote Sensing Symposium.

[7]  K. Qin,et al.  The pixel rectangle index used in object based building extraction from high resolution images , 2014 .

[8]  Jinfei Wang,et al.  Detection of buildings from Landsat-7 ETM+ and SPOT panchromatic data in Beijing, China , 2002, IEEE International Geoscience and Remote Sensing Symposium.

[9]  Alejandro Hinojosa-Corona,et al.  A Genetic Programming Approach to Estimate Vegetation Cover in the Context of Soil Erosion Assessment , 2011 .

[10]  Pharmd Candidate,et al.  USING HIGH-RESOLUTION AERIAL PHOTOGRAPHY AND NEURAL NETWORKS TO INVENTORY PROPERTIES AT RISK OF EARTHQUAKES , 2006 .

[11]  Curt H. Davis,et al.  Automated Building Extraction from High-Resolution Satellite Imagery in Urban Areas Using Structural, Contextual, and Spectral Information , 2005, EURASIP J. Adv. Signal Process..

[12]  Nilanchal Patel,et al.  Extraction of impervious features from spectral indices using artificial neural network , 2015, Arabian Journal of Geosciences.

[13]  Florence Tupin,et al.  Building extraction and 3D reconstruction in urban areas from high-resolution optical and SAR imagery , 2009, 2009 Joint Urban Remote Sensing Event.

[14]  Martin Herold,et al.  Spectral resolution requirements for mapping urban areas , 2003, IEEE Trans. Geosci. Remote. Sens..

[15]  R. Nemani,et al.  MULTI-SENSOR MULTI-RESOLUTION IMAGE FUSION FOR IMPROVED VEGETATION AND URBAN AREA CLASSIFICATION , 2015 .

[16]  Bor-Chen Kuo,et al.  A Kernel-Based Feature Selection Method for SVM With RBF Kernel for Hyperspectral Image Classification , 2014, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[17]  Hamid Ebadi,et al.  Automated Building Extraction from High-Resolution Satellite Imagery Using Spectral and Structural Information Based on Artificial Neural Networks , 2007 .

[18]  Alexandre Carleer,et al.  The VHR data region-based classification possibilities in the framework of Control with Remote Sensing of European CAP , 2005 .

[19]  Huiping Liu,et al.  THE DECISION TREE ALGORITHM OF URBAN EXTRACTION FROM MULTI-SOURCE IMAGE DATA , 2009 .

[20]  B. Pinty,et al.  GEMI: a non-linear index to monitor global vegetation from satellites , 1992, Vegetatio.

[21]  X. H,et al.  A new index for delineating built-up land features in satellite imagery , 2008 .

[22]  P. Shi,et al.  Improving the normalized difference built-up index to map urban built-up areas using a semiautomatic segmentation approach , 2009 .

[23]  D. Roy,et al.  The availability of cloud-free Landsat ETM+ data over the conterminous United States and globally , 2008 .

[24]  M. Turker,et al.  BUILDING DETECTION FROM PAN-SHARPENED IKONOS IMAGERY THROUGH SUPPORT VECTOR MACHINES CLASSIFICATION , 2010 .

[25]  A. J. Luis,et al.  A Rapid Extraction of Water Body Features from Antarctic Coastal Oasis Using Very High-Resolution Satellite Remote Sensing Data , 2015 .

[26]  Yi Lu,et al.  AUTOMATIC BUILDING EXTRACTION FOR 3 D TERRAIN RECONSTRUCTION USING INTERPRETATION TECHNIQUES , 2003 .

[27]  C. Fraser,et al.  Automatic Building Extraction From LIDAR Data Covering Complex Urban Scenes , 2014 .

[28]  Hanqiu Xu.  Modification of normalised difference water index (NDWI) to enhance open water features in remotely sensed imagery , 2006 .

[29]  P. Horkaew,et al.  RIVER BOUNDARY DELINEATION FROM REMOTELY SENSED IMAGERY BASED ON SVM AND RELAXATION LABELING OF WATER INDEX AND DSM , 2015 .

[30]  Nicholas Kalouptsidis,et al.  Nearest neighbor pattern classification neural networks , 1994, Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94).

[31]  Rama Rao Nidamanuri,et al.  Semantic labelling of urban point cloud data , 2014 .

[32]  Mohamed Saber Naceur,et al.  Support Vector Machine for Remote Sensing image classification , 2013 .

[33]  Helmi Zulhaidi Mohd Shafri,et al.  A novel spectral index to automatically extract road networks from WorldView-2 satellite imagery , 2015 .

[34]  Yonghak Song,et al.  BUILDING EXTRACTION FROM HIGH RESOLUTION COLOR IMAGERY BASED ON EDGE FLOW DRIVEN ACTIVE CONTOUR AND JSEG , 2008 .

[35]  Guo Zhang,et al.  HIGH EFFICIENT CLASSIFICATION ON REMOTE SENSING IMAGES BASED ON SVM , 2008 .

[36]  Xiaoling Chen,et al.  A spectral index for highlighting forest cover from remotely sensed imagery , 2014, Asia-Pacific Environmental Remote Sensing.

[37]  Ching Y. Suen,et al.  Application of majority voting to pattern recognition: an analysis of its behavior and performance , 1997, IEEE Trans. Syst. Man Cybern. Part A.

[38]  Lizhong Hua,et al.  A New Decision Tree Classification Approach for Extracting Urban Land from Landsat TM in a Coastal City, China , 2012, 2012 Fourth International Symposium on Information Science and Engineering.

[39]  P. Gong,et al.  Object-based Detailed Vegetation Classification with Airborne High Spatial Resolution Remote Sensing Imagery , 2006 .

[40]  R. Suzuki,et al.  ESTIMATION TREE DENSITY AS OBJECT-BASED IN ARID AND SEMI-ARID REGIONS USING ALOS , 2012 .

[41]  Hanqiu Xu.  Extraction of Urban Built-up Land Features from Landsat Imagery Using a Thematicoriented Index Combination Technique , 2007 .

[42]  Isabelle Bloch,et al.  Application of Dempster-Shafer evidence theory to unsupervised classification in multisource remote sensing , 1997, IEEE Trans. Geosci. Remote. Sens..

[43]  Naci Yastikli,et al.  Automatic building extraction using LiDAR and aerial photographs , 2013 .

[44]  Jiang Xu,et al.  Coastline Extraction Using Support Vector Machine from Remote Sensing Image , 2013, J. Multim..

[45]  Kurt Kubik,et al.  Automatic Building Detection Using the Dempster-Shafer Algorithm , 2006 .

[46]  Norbert Haala,et al.  Building parameters extraction from remote-sensing data and GIS analysis for the derivation of a building taxonomy of settlements – a contribution to flood building susceptibility assessment , 2015 .

[47]  Driss Mammass,et al.  SVM Classification of Urban High-Resolution Imagery Using Composite Kernels and Contour Information , 2013 .

[48]  David P. Roy,et al.  Accessing free Landsat data via the Internet: Africa's challenge , 2010 .

[49]  Liangpei Zhang,et al.  Building Change Detection From Multitemporal High-Resolution Remotely Sensed Images Based on a Morphological Building Index , 2014, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[50]  A. Huete.  A soil-adjusted vegetation index (SAVI) , 1988 .

[51]  M. Erdogan.  RESOLUTION MERGE OF 1:35.000 SCALE AERIAL PHOTOGRAPHS WITH LANDSAT 7 ETM IMAGERY , 2008 .

[52]  Fabio Roli,et al.  Support vector machines for remote sensing image classification , 2001, SPIE Remote Sensing.

[53]  Jin A. Lee.  Development of an urban classification method using a built-up index , 2010 .

[54]  M. Sharifi,et al.  A NEW PROMPT FOR BUILDING EXTRACTION IN HIGH RESOLUTION REMOTELY SENSED IMAGERY , 2013 .

[55]  Waqar Mirza Muhammad.  Development of New Indices for Extraction of Built-Up Area & Bare Soil from Landsat Data , 2012 .

[56]  S. Arekhi,et al.  Remote sensing and GIS for mapping and monitoring land cover and land use changes using support vector machine algorithm ( Case study : Ilam dam watershed ) , 2014 .